Kolloquiumsvortrag 25. November 2025, Anton Wunsch (Betreuer: Muhammad)
Enhancing Cybersecurity: LLM-based Intrusion Detection System.
The threat of cyberattacks is challenging modern digital infrastructure. While traditional intrusion detection systems are already effective, they have certain limitations, for example, in detecting new attack patterns. With the emergence of large language models, many new application fields have opened, including cybersecurity. This thesis explores how different approaches, such as retrieval-augmented generation, fine-tuning, and in-context learning, can be applied for the classification of real-time traffic as either attack or benign. The goal is to evaluate the feasibility, strengths, and weaknesses of each approach for intrusion detectio.
Uhrzeit: 10:15 Uhr
Ort: Raum 04.137, Martensstr. 3, Erlangen
oder
Zoom-Meeting beitreten:
https://fau.zoom-x.de/j/68350702053?pwd=UkF3aXY0QUdjeSsyR0tyRWtLQ0hYUT09
Meeting-ID: 683 5070 2053
Kenncode: 647333